Adds muscle to the female protagonist of your video.

Important: This model is 100% fictitious and is not based on images of any real person. The data set for the model was generated from still image checkpoints and has evolved from there using only AI rendering. No images (neither actual nor AI-generated) of any real person were ever involved in the making of this model.

Version 3.0 Update

This version of the model is compiled from the Wan 2.2 Text-to-Video model, so it includes both High and Low noise models and does a much better job with full motion and details. The two models, High and Low, can be used together or separately for different looks depending on what you want in your video.

• High Only - Less muscle definition, less veiny (usually). Makes the woman look more like an athlete or bodybuilder woman on an average day. Face tends to look more bodybuilder-like when prompting for big muscles. The sample videos in the High Noise model version are made with ONLY the High Noise model.

• Both High and Low - Lots more skin and muscle detail and definition. The women look like they're only days away from a fitness or bodybuilding competition after weeks of hard training and a careful diet. The sample videos in the Low Noise model version are made with BOTH the High and Low noise models.

• Low Only - Less size overall, but can still have high definition. Adds muscle detail to a body that was already mostly made by the High Noise stage. Great for "fitness model" body type.

See the sample videos for a couple of comparison clips. I'm including all the prompt text in the sample videos so you can see how different body descriptions lead to different looks in the videos.

The dataset includes full nudes, although it's not always perfect so sometimes you will want to add the LoRA of your choice to add detail. There were no faces in the dataset, so you should be able to add this model to any character without wrecking the face. There must be a bias in the dataset for cropped tops and exposed stomachs since that comes up often in the videos I've made, but you can easily fix that with additional prompting.

LoRA strength values can go above 1.00 for a slightly stronger effect. Obviously, the strength can be reduced as low as you want to reduce the impact. High noise should never go above 2.00. Low noise should stay below 2.50 or you will see some artifacts in the output.

ComfyUI workflow guidance

For my current favorite ComfyUI configuration, please refer to my article for all the necessary info you'll need to make the most of my Wan 2.1 LoRAs in Wan 2.2 videos.

VERSION 2

UPDATE: For the best results using Version 1 or 2, please give my workflow a try. This workflow is what I use to make all my videos using my models and it produces great results in Wan 2.2 using LoRAs that were created with the Wan 2.1 model.

Most of this text has been re-written to account for Version 2. There were too many changes in how the model behaves to just put the changes in the version notes. If you've been using Version 1, please re-read these notes as they may help.

The key phrase is "muscular woman" as in "a muscular woman is walking in the park".

• 0.25 - 0.75 is an athletic woman who exercises regularly and looks a little muscular

• 0.75 - 1.50 is an obviously muscular woman who works out and lifts weights regularly

• above 1.5 is a bodybuilder level of muscular, but with you will see a little oversaturation in the body above 3.0.

For enhanced results without the penalty of saturation and less motion, you can use prompt hints. Wan 2.2 is especially good at respecting prompt descriptions for this LoRA. A simple change is to say "an extremely muscular woman", but you can go into more specific detail if you want. Beware of using the word "bodybuilder" with Wan, however, as that will likely influence the poses and motions that you get. Wan seems to know about bodybuilder competitions and posing, and those influences will appear in your video if you use that word in your prompt. Also, you should be aware that Wan understands the context of the scene. If your scene is set in a gym lifting weights, the results will be quite a bit more muscular than the same prompt and seed set in a restaurant.

This model will also increase breast size slightly, but not significantly. If you want to change the bust size more, a combination of prompting and additional LoRAs will help. This muscular LoRA does play well with others.

Notes on Version 2 LoRA training: The more I used version 1, the more annoyed I was getting at the oversaturation of the faces. With this version, I used the same data set of about 200 images, but I used some comfyui nodes to automatically mask out every face with a transparent rectangle. The hair is still visible, and nothing else in the images was changed. My captions were all very simple and only had a couple of variations to counter a bias I noticed from version 1:

a portrait of a muscular woman. her face is censored. (she has her hands on her hips.) (her hands are closed in fists.)

The last two sentences were optional, I added them to whichever images needed them. It seemed like too many of my data set pictures had bodybuilder poses with closed fists and hands on hips, making a lot of the output videos carry that bias. This Version 2 does not seem to have that issue. Amazingly, I am publishing Epoch number THREE out of 20. With limited captioning and a broad data set, I was amazed at how quickly and strongly Wan learned the model. With such a low epoch number, it looks like this model preserves a great deal of the motion and other details of the scene that you would see if you weren't using the LoRA at all, which is a great sign. After publishing all the samples, I'll be posting a series of videos that were all the same clip and prompt ranging from no LoRA at all up to 4.0 and a little beyond so you can see the changes in motion and detail.

I hope you all enjoy this dose of strong women.